Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

Prateek Yadav, Peter Hase, Mohit Bansal

Keywords: Explainability, Interpretability, Counterfactuals, Algorithmic Recourse, Black-box Models, Machine Learning, Accountability, Consumer Protection, Adverse Action Notices

Abstract: The problem of identifying algorithmic recourse for people affected by machine learning model decisions has received much attention recently. Existing approaches for recourse generation obtain solutions using properties like diversity, proximity, sparsity, and validity. Yet, these objectives are only heuristics for what we truly care about, which is whether a user is satisfied with the recourses offered to them. Some recent works try to model user-incurred cost, which is more directly linked to user satisfaction. But they assume a single global cost function that is shared across all users. This is an unrealistic assumption when users have dissimilar preferences about their willingness to act upon a feature and different costs associated with changing that feature. In this work, we formalize the notion of user-specific cost functions and introduce a new method for identifying actionable recourses for users. By default, we assume that users' cost functions are hidden from the recourse method, though our framework allows users to partially or completely specify their preferences or cost function. We propose an objective function, Expected Minimum Cost (EMC), based on two key ideas: (1) when presenting a set of options to a user, it is vital that there is at least one low-cost solution the user could adopt; (2) when we do not know the user's true cost function, we can approximately optimize for user satisfaction by first sampling plausible cost functions, then finding a set that achieves a good cost for the user in expectation. We optimize EMC with a novel discrete optimization algorithm, Cost-Optimized Local Search (COLS), which is guaranteed to improve the recourse set quality over iterations. Experimental evaluation on popular real-world datasets with simulated user costs demonstrates that our method satisfies up to 25.89 percentage points more users compared to strong baseline methods. Using standard fairness metrics, we also show that our method can provide more fair solutions across demographic groups than comparable methods, and we verify that our method is robust to misspecification of the cost function distribution.

One-sentence Summary: Providing individualized recourse to users with unknown feature preferences and cost functions.

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2111.01235/code)